Snow cleaning and shed covering progress monitoring method, device and equipment based on Sentinel-2 image and medium

Abstract

The invention provides a snow clearing and shed covering progress monitoring method, device and equipment based on Sentinel-2 images and a medium, and the method comprises the steps: obtaining multi-stage Sentinel-2 image data of snow clearing and shed covering within a preset time range, and constructing a time sequence image data set; obtaining vector basic data of the greenhouse land, and cutting the time sequence image data set based on the vector basic data to obtain target Sentinel-2 image data; constructing a greenhouse accumulated snow index based on the normalized difference snow index and the blue wave band reflectivity; according to the method, a greenhouse accumulated snow index grid map of target Sentinel-2 image data is calculated, a Fisher-Jenks algorithm is adopted to classify snow removal and greenhouse covering, and the area and proportion of classification results are counted, so that the problems that the snow removal and greenhouse covering monitoring effect is weak and measures cannot be taken in time in a greenhouse field due to the fact that accumulated snow in a complex terrain or when a snow layer is weak cannot be recognized are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural remote sensing applications, and in particular to a method, device, equipment and medium for monitoring snow clearing and shed closing progress based on Sentinel-2 images. Background Art

[0002] "Snow clearing and shading" is an important task in agricultural greenhouse management, which is to promptly remove the snow accumulated on the top of the greenhouse after snowfall, and to reinforce and protect the structure of the greenhouse to ensure that it can remain stable in cold weather or after snowfall. In agricultural production, especially in greenhouses in the Northeast, snow accumulation poses a serious threat to the safety of the greenhouse. Excessive snow accumulation will increase the structural burden of the greenhouse, causing damage to the roof or even collapse, thus affecting the growth of crops in the greenhouse. Therefore, timely clearing of snow and shading the greenhouse after snowfall is the key to ensuring the normal operation of the greenhouse.

[0003] Traditional methods for monitoring the progress of snow clearing and greenhouse covering mostly rely on manual inspection information reporting. These methods are time-consuming and labor-intensive, and cannot fully cover the greenhouse area, resulting in low efficiency. Manual methods are greatly affected by factors such as weather and time, and the monitoring results are prone to errors. The progress of snow clearing and greenhouse covering work cannot be grasped in real time, resulting in the inability to discover problems and take measures in a timely manner. NDSI Normalized Difference Snow Index is a method used for snow detection in remote sensing. It identifies snow cover by comparing green light and short-wave infrared reflectivity. It is often used in snow detection, distinguishing snow from clouds, frozen lake detection, glacier mapping and other fields. It is rarely used in agricultural scenarios and has certain limitations in actual application. It cannot identify snow accumulation in complex terrain or when the snow layer is thin, and the effect of monitoring snow clearing and greenhouse covering in greenhouses is weak.

[0004] Therefore, it is urgent to propose a method for monitoring the progress of snow clearing and roof covering based on Sentinel-2 images to solve the technical problem that the effect of snow clearing and roof covering in greenhouses is weak and timely measures cannot be taken due to the inability to identify snow accumulation in complex terrain or thin snow layer. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the present disclosure provides a method, device, equipment and medium for monitoring the progress of snow clearing and roof covering based on Sentinel-2 images, so as to solve the technical problems in the related art that the snow clearing and roof covering effect in the greenhouse cannot be monitored due to the inability to identify snow accumulation in complex terrain or thin snow layer, resulting in weak effect and failure to take timely measures.

[0006] One or more embodiments of this specification provide a method for monitoring snow clearing and snow cover progress based on Sentinel-2 images, including the following steps:

[0007] Acquire multiple periods of Sentinel-2 image data for snow clearing and shed closing within a preset time range and construct a time series image dataset;

[0008] Acquire vector basic data of the greenhouse, and clip the time series image data set based on the vector basic data to obtain target Sentinel-2 image data of the greenhouse;

[0009] The greenhouse snow accumulation index is constructed based on the normalized difference snow index and blue band reflectance;

[0010] Calculate the greenhouse snow accumulation index raster map of the target Sentinel-2 image data, use the Fisher-Jenks algorithm to classify snow removal and greenhouse closing, and count the area and proportion of the classification results.

[0011] Preferably, the step of clipping the time series image data set based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse specifically comprises the following steps:

[0012] The gdal.Warp function of Python is used to clip the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

[0013] Preferably, the greenhouse snow index calculation formula is as follows:

[0014] GSCI=NDSI*(1-R blue );

[0015] Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blue Represents the blue band reflectance.

[0016] Preferably, the greenhouse snow accumulation index grid map of the target Sentinel-2 image data is calculated, the Fisher-Jenks algorithm is used to classify snow removal and greenhouse closing, and the area and proportion of the classification results are statistically calculated, which specifically includes the following steps:

[0017] The greenhouse snow index grid map of the target Sentinel-2 image data is calculated using python's gdal and numpy functions;

[0018] Fisher-Jenks algorithm was used to classify snow-cleared sheds, and the classification results were: sheds that had been cleared of snow and sheds that had not been cleared of snow;

[0019] Python is used to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, and the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot are obtained to obtain the area and proportion of the statistical classification results.

[0020] One or more embodiments of this specification provide a snow-clearing and greenhouse-covering progress monitoring device based on Sentinel-2 images, including an image data acquisition module, an image data cropping module, a greenhouse snow accumulation index construction module, and a classification and statistics module;

[0021] The image data acquisition module is used to acquire multiple periods of Sentinel-2 image data of snow clearing and shed closing within a preset time range to construct a time series image data set;

[0022] The image data clipping module is used to obtain vector basic data of the greenhouse, and clip the time series image data set based on the vector basic data to obtain target Sentinel-2 image data of the greenhouse;

[0023] The greenhouse snow index construction module is used to construct the greenhouse snow index based on the normalized difference snow index and the blue band reflectivity;

[0024] The classification statistics module is used to calculate the greenhouse snow index grid map of the target Sentinel-2 image data, use the Fisher-Jenks algorithm to classify snow clearing and greenhouse closing, and count the area and proportion of the classification results.

[0025] Preferably, the image data clipping module is configured to use Python's gdal.Warp function to clip the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

[0026] Preferably, the greenhouse snow index calculation formula is as follows:

[0027] GSCI=NDSI*(1-R blue );

[0028] Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blue Represents the blue band reflectance.

[0029] Preferably, the classification and statistics module includes a calculation unit, a classification unit and a statistics unit;

[0030] The calculation unit is used to calculate the greenhouse snow index grid map of the target Sentinel-2 image data by using python's gdal and numpy functions;

[0031] The classification unit is used to classify snow-cleared sheds using the Fisher-Jenks algorithm to obtain classification results: snow-cleared sheds and uncleared sheds;

[0032] The statistical unit is used to use Python to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, obtain the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot, and obtain the area and proportion of the statistical classification results.

[0033] One or more embodiments of the present specification provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for monitoring the progress of snow clearing and shed covering based on Sentinel-2 images when executing the computer program.

[0034] One or more embodiments of the present specification provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for monitoring the progress of snow clearing and snow shed covering based on Sentinel-2 images.

[0035] The present disclosure provides a method, device, equipment and medium for monitoring the progress of snow clearing and greenhouse covering based on Sentinel-2 images. The advantages are that by acquiring multiple periods of Sentinel-2 image data of snow clearing and greenhouse covering within a preset time range, a time series image data set is constructed, which can capture the actual situation of snow clearing and greenhouse covering work at different time nodes, and present the dynamic change process of snow accumulation and greenhouse covering status in the greenhouse area over time; the vector basic data of the greenhouse is acquired, and the time series image data set is clipped based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse, which can accurately extract the image information related to the greenhouse, eliminate the interference of irrelevant surrounding areas, so that the subsequent analysis can only focus on the specific area where the greenhouse is located, avoid the influence of irrelevant data on the analysis of snow clearing and greenhouse covering progress, and improve the analysis efficiency and pertinence; based on the normalized difference The greenhouse snow index is constructed by using the abnormal snow index and the blue band reflectivity, which can more effectively highlight the characteristic information of snow in the greenhouse area. Compared with a single indicator, the index comprehensively considers the reflection of snow reflection characteristics in different bands, making the performance of snow in the image data more significant, and facilitating more accurate identification and distinction of snow from other landforms; the greenhouse snow index raster map of the target Sentinel-2 image data is calculated, and the Fisher-Jenks algorithm is used to classify snow clearing and greenhouse covering, and the area and proportion of the classification results are statistically analyzed to visually display the distribution of snow-related characteristics in the greenhouse area in a visual way, and then classified by the Fisher-Jenks algorithm, which can clearly divide the greenhouse area into different snow clearing and greenhouse covering status categories, so that the entire snow clearing and greenhouse covering progress is clear at a glance, which is convenient for intuitive understanding and analysis, and timely feedback of progress information to ensure the safety of the greenhouse. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 A flowchart of a method for monitoring snow clearing and snow cover progress based on Sentinel-2 images provided in one or more embodiments of this specification;

[0038] Figure 2 A flow chart of dynamic monitoring of snow clearing and shed covering progress provided by one or more embodiments of this specification;

[0039] Figure 3The dynamic monitoring diagram of the progress of snow clearing and shed covering provided by one or more embodiments of this specification, (a) is a dynamic monitoring diagram of the progress of snow clearing and shed covering based on Sentinel-2 images on February 28, 2024 in the experiment, (b) is a dynamic monitoring diagram of the progress of snow clearing and shed covering based on Sentinel-2 images on March 4, 2024 in the experiment, (c) is a dynamic monitoring diagram of the progress of snow clearing and shed covering based on Sentinel-2 images on March 9, 2024 in the experiment, (d) is a dynamic monitoring diagram of the progress of snow clearing and shed covering based on Sentinel-2 images on March 9, 2024 in the experiment;

[0040] Figure 4 A time-varying graph of the cumulative snow-clearing and greenhouse-covering area and cumulative ratio of the greenhouse in Hongwei Farm provided in one or more embodiments of this specification;

[0041] Figure 5 A schematic diagram of the structure of a snow-clearing and snow-covering progress monitoring device based on Sentinel-2 images provided in one or more embodiments of this specification;

[0042] Figure 6 A schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0044] The present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0045] Method Embodiment

[0046] According to an embodiment of the present invention, a method for monitoring the progress of snow clearing and snow cover based on Sentinel-2 images is provided. Figure 1 As shown, it is a flow chart of the method for monitoring the progress of snow clearing and covering the shed based on Sentinel-2 images provided in this embodiment. According to the method for monitoring the progress of snow clearing and covering the shed based on Sentinel-2 images in an embodiment of the present invention, the following steps are included:

[0047] S110, obtaining multiple periods of Sentinel-2 image data of snow-clearing and roof-covering within a preset time range, and constructing a time series image dataset. Specifically, multiple periods of Sentinel-2 image data are downloaded through GEE (Google Earth Engine) within the snow-clearing and roof-covering time range, and radiation calibration, atmospheric correction and geometric correction are performed on the multiple periods of Sentinel-2 image data to construct a time series image dataset.

[0048] S120, obtaining the vector basic data of the greenhouse. The vector basic data of the greenhouse is manually confirmed and identified to ensure the accuracy of the research. The time series image dataset is cropped based on the vector basic data, and mask extraction is performed using python to obtain the target Sentinel-2 image data of the greenhouse.

[0049] S130. Construct a greenhouse snow accumulation index based on the normalized difference snow index and the blue band reflectivity.

[0050] S140, calculating the greenhouse snow accumulation index grid map of the target Sentinel-2 image data, using the Fisher-Jenks algorithm to classify snow removal and greenhouse closing, and counting the area and proportion of the classification results.

[0051] The method provided in this embodiment constructs a time series image dataset by acquiring multiple periods of Sentinel-2 image data of snow clearing and greenhouse closing within a preset time range, which can capture the actual situation of snow clearing and greenhouse closing work at different time nodes, and present the dynamic change process of snow accumulation and greenhouse closing status in the greenhouse area over time; obtains vector basic data of the greenhouse, and cuts the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse, which can accurately extract image information related to the greenhouse and eliminate interference from surrounding irrelevant areas, so that subsequent analysis can focus only on the specific area where the greenhouse is located, avoiding the influence of irrelevant data on the analysis of snow clearing and greenhouse closing progress, and improving analysis efficiency and pertinence; constructs a greenhouse snow accumulation index based on the normalized difference snow index and the blue band reflectivity The number can more effectively highlight the characteristic information of snow accumulation in the greenhouse area. Compared with a single indicator, the index comprehensively considers the reflection of snow reflection characteristics in different bands, making the performance of snow accumulation in the image data more significant, and facilitating more accurate identification and distinction of snow accumulation from other landforms; the greenhouse snow accumulation index raster map of the target Sentinel-2 image data is calculated, and the Fisher-Jenks algorithm is used to classify snow clearing and greenhouse covering, and the area and proportion of the classification results are statistically analyzed to visually display the distribution of snow-related characteristics in the greenhouse area. The Fisher-Jenks algorithm is then used for classification, and the greenhouse area can be clearly divided into different snow clearing and greenhouse covering status categories, so that the entire snow clearing and greenhouse covering progress is clear at a glance, which is convenient for intuitive understanding and analysis, and timely feedback of progress information to ensure the safety of the greenhouse.

[0052] In one embodiment, the time series image data set is clipped based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse, which specifically includes the following steps:

[0053] The gdal.Warp function of Python is used to clip the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

[0054] The method provided in this embodiment can accurately extract image data corresponding to the greenhouse, eliminate interference from irrelevant areas, ensure that the data fits the actual area of ​​the greenhouse in spatial scope, and provide an accurate and focused image basis for subsequent related analysis such as greenhouse snow clearing and greenhouse closing progress monitoring.

[0055] In one embodiment, the greenhouse snow index calculation formula is as follows:

[0056] GSCI=NDSI*(1-R blue );

[0057] Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blue Represents the blue band reflectance.

[0058] The GSCI index (Greenhouse Snow-Cover Index) can distinguish greenhouse snow accumulation from snow clearing based on the complementarity of NDSI (Normalized Difference Snow Index) and Blue (blue band) in detecting snow and ice. NDSI has been widely used for snow detection, which uses the reflection difference between the green band and the short-wave infrared band to distinguish between snow and non-snow areas. However, in some cases, the Blue band can also provide additional differentiation capabilities, especially in the difference in the reflection characteristics of water and snow. In the process of snow clearing in greenhouses, the Blue band can highlight the effect of snow clearing. Therefore, combining the Blue band with NDSI to construct the GSCI index can improve the accuracy of snow clearing and greenhouse monitoring, especially in complex terrain or when the snow layer is thin.

[0059] In one embodiment, a greenhouse snow accumulation index grid map of the target Sentinel-2 image data is calculated, the Fisher-Jenks algorithm is used to classify snow removal and greenhouse closing, and the area and proportion of the classification results are counted, specifically including the following steps:

[0060] The greenhouse snow index raster map of the target Sentinel-2 image data was calculated using Python's gdal and numpy functions.

[0061] The Fisher-Jenks algorithm was used to classify snow-cleared sheds, and the classification results were: cleared sheds and uncleared sheds. Specifically, the data was read through the pandas library, the GSCI index grid map numerical data was stored in a list, the function in the pysal library was used to calculate the optimal bins, the continuous GSCI index grid numerical data was divided into two different levels, and then the Fisher-Jenks function in the pysal library was used to classify the data into cleared sheds and uncleared sheds.

[0062] Python is used to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, and the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot are obtained to obtain the area and proportion of the statistical classification results.

[0063] Area_Snow-cleared shed=SUM(the total number of pixels where snow has been cleared)*(10*10) / 666.67;

[0064] Area_Uncleared snow and shed = SUM (the total number of pixels without cleared snow and shed) * (10 * 10) / 666.67;

[0065] Proportion_Snow-cleared shed=Area_Snow-cleared shed / Area_Greenhouse;

[0066] Proportion_Uncleared snow covered shed = Area_Uncleared snow covered shed / Area_Greenhouse land;

[0067] Among them, NDSI is the normalized difference snow index, and the calculation formula is as follows:

[0068]

[0069] Green represents the green band; SWIR1 represents the shortwave infrared band.

[0070] The method provided in this embodiment uses Python related functions and algorithms to accurately calculate the greenhouse snow accumulation index of the target image data and generate a raster map. The classification algorithm is used to distinguish the snow clearing and greenhouse covering status, and then the vector data is divided into zones and statistics. Finally, the area and proportion of the snow clearing and greenhouse covering conditions of each large greenhouse plot are quantitatively presented, providing accurate data support for intuitively grasping the progress of snow clearing and greenhouse covering and carrying out targeted agricultural management.

[0071] The following is a further explanation using Hongwei Farm in Jiansanjiang District, Heilongjiang Province as a specific implementation case:

[0072] Taking Hongwei Farm in Jiansanjiang District, Heilongjiang Province as an example, the progress of snow clearing and greenhouse covering in Hongwei Farm was dynamically monitored. Figure 2 As shown, it is a flowchart of the dynamic monitoring of the progress of snow clearing and shed covering provided in this embodiment. The method for monitoring the progress of snow clearing and shed covering based on Sentinel-2 images is as follows:

[0073] S1. Conduct an investigation based on the time of snow clearing and roof covering, determine the time range for image acquisition, obtain the measured data of snow clearing and roof covering, and observe the sample characteristics.

[0074] The measured data of snow clearing and shed covering are the data obtained in advance from the database, combined with visual interpretation to establish a sample set. After field investigation, the time range of snow clearing and shed covering at Hongwei Farm in Jiansanjiang District, Heilongjiang Province is from mid-to-late February to early to mid-March each year. After snow clearing and shed covering, the Sentinel-2 image features are dark gray with low reflectivity, while the Sentinel-2 image features of sheds not cleared and covered with snow are covered with snow and have high reflectivity. The satellite remote sensing image described in this embodiment is a satellite remote sensing image that includes the snow clearing and shed covering area to be monitored.

[0075] S2. Download multiple periods of Sentinel-2 image data according to the time range of S1, and ensure that the data has been radiometrically calibrated, atmospherically corrected, and geometrically corrected to construct a time series image dataset. The Sentinel-2 image data downloaded from the Google Earth Engine platform has undergone basic preprocessing.

[0076] S3. Obtain the basic vector data of greenhouses in the study area. The vector data of greenhouses was obtained from Beidahuang Group and manually confirmed and identified to ensure the accuracy of the research. The data format is SHP and the coordinates are WGS-1984.

[0077] S4. Use the greenhouse vector basic data in S3 to crop the satellite image dataset in S2 to obtain the Sentinel-2 image data of the greenhouse in the study area, which can be cropped using Python's gdal.Warp.

[0078] S5. Calculate the newly constructed greenhouse snow cover index GSCI based on the cropped satellite remote sensing image in S4.

[0079] By using Python's gdal and numpy to perform calculations, the operating efficiency is improved, the high software licensing fees are eliminated, and the cost is reduced. The GSCI index calculation formula is as follows:

[0080] GSCI=NDSI*(1-R blue );

[0081] GSCI: Greenhouse Snow Cover Index

[0082] NDSI: Normalized Difference Snow Index

[0083] R blue : Blue band reflectivity

[0084] S6. For the newly constructed GSCI index grid map calculated in S5, use python to perform Fisher-Jenks algorithm classification to obtain the classification results, which are divided into cleared snow and uncleared snow sheds. At the same time, the area and proportion of cleared snow and uncleared snow sheds are counted.

[0085] First, in the Python environment, the Fisher-Jenks algorithm was used to classify the greenhouse snow accumulation index GSCI index grid map. The data was read through the pandas library, the GSCI index grid map numerical data was stored in a list, the optimal bins were calculated using the function in the pysal library, the continuous GSCI index grid numerical data was divided into two different levels, and then the Fisher-Jenks function in the pysal library was used to classify the data into cleared snow and not cleared snow.

[0086] Then, the area and proportion of the cleared and uncleaned greenhouses are counted. Python is used to perform zoning statistics on the raster data that has been classified in the previous step according to the existing greenhouse vector basic data, and the count and sum of the cleared and uncleaned pixels of each greenhouse plot are counted.

[0087] Area_Snow-cleared roof = SUM (total number of pixels with snow-cleared roof) * (10 * 10) / 666.67

[0088] Area_Uncleared snow and shed = SUM (the total number of pixels without cleared snow and shed) * (10 * 10) / 666.67

[0089] Proportion_Snow cleared and covered = Area_Snow cleared and covered / Area_Greenhouse

[0090] Proportion_Uncleared snow and covered shed=Area_Uncleared snow and covered shed / Area_Greenhouse

[0091] Note: NDSI is the Normalized Difference Snow Index, and the calculation formula is as follows:

[0092]

[0093] Green represents the green band; SWIR1 represents the shortwave infrared band.

[0094] This experiment takes Hongwei Farm in Jiansanjiang District, Heilongjiang Province as an example to dynamically monitor the progress of snow clearing and greenhouse covering in Hongwei Farm. The multi-period Sentinel-2 image data of snow clearing and greenhouse covering within the preset time range and the measured data of snow clearing and greenhouse covering are combined to form sample features. The Kappa coefficient is used to combine the sample features and the classification results of snow clearing and greenhouse covering of the greenhouse snow accumulation index to verify the accuracy, improve the accuracy of snow clearing and greenhouse covering progress monitoring, and the overall accuracy can reach 0.90. Experimental results Figure 3-Figure 4 shown.

[0095] Device Embodiment

[0096] According to an embodiment of the present invention, a snow clearing and snow shed progress monitoring device based on Sentinel-2 images is provided. Figure 5 As shown, it is a structural schematic diagram of the snow-clearing and greenhouse-covering progress monitoring device based on Sentinel-2 images provided in this embodiment. According to the embodiment of the present invention, the snow-clearing and greenhouse-covering progress monitoring device based on Sentinel-2 images includes an image data acquisition module 51, an image data cropping module 52, a greenhouse snow accumulation index construction module 53 and a classification statistics module 54.

[0097] The image data acquisition module 51 is used to acquire multiple periods of Sentinel-2 image data of snow clearing and rooftop closing within a preset time range to construct a time series image data set.

[0098] The image data clipping module 52 is used to obtain vector basic data of the greenhouse, and clip the time series image data set based on the vector basic data to obtain target Sentinel-2 image data of the greenhouse.

[0099] The greenhouse snow index construction module 53 is used to construct the greenhouse snow index based on the normalized difference snow index and the blue band reflectivity.

[0100] The classification and statistics module 54 is used to calculate the greenhouse snow accumulation index grid map of the target Sentinel-2 image data, use the Fisher-Jenks algorithm to classify snow removal and greenhouse closing, and count the area and proportion of the classification results.

[0101] The device provided in this embodiment, the image data acquisition module 51 acquires multiple periods of Sentinel-2 image data of snow clearing and greenhouse closing within a preset time range, constructs a time series image data set, can capture the actual situation of snow clearing and greenhouse closing work at different time nodes, and presents the dynamic change process of snow accumulation and greenhouse closing status in the greenhouse area over time; the image data cropping module 52 acquires the vector basic data of the greenhouse, and crops the time series image data set based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse, which can accurately extract the image information related to the greenhouse, eliminate the interference of irrelevant surrounding areas, so that subsequent analysis can focus only on the specific area where the greenhouse is located, avoid the influence of irrelevant data on the analysis of snow clearing and greenhouse closing progress, and improve the analysis efficiency and pertinence; the greenhouse snow accumulation index construction module 53 is based on the normalized difference snow index and the blue wave The greenhouse snow accumulation index is constructed based on the segment reflectivity, which can more effectively highlight the characteristic information of snow accumulation in the greenhouse area. Compared with a single indicator, the index comprehensively considers the reflection of snow accumulation reflection characteristics in different bands, making the performance of snow accumulation in the image data more significant, and facilitating more accurate identification and distinction of snow accumulation from other landforms; the classification and statistics module 54 calculates the greenhouse snow accumulation index raster map of the target Sentinel-2 image data, adopts the Fisher-Jenks algorithm to classify snow clearing and greenhouse covering, and statistically calculates the area and proportion of the classification results, so as to visually display the distribution of snow-related characteristics in the greenhouse area, and then classifies it through the Fisher-Jenks algorithm, which can clearly divide the greenhouse area into different snow clearing and greenhouse covering status categories, so that the entire snow clearing and greenhouse covering progress is clear at a glance, which is convenient for intuitive understanding and analysis, and timely feedback of progress information to ensure the safety of the greenhouse.

[0102] In one embodiment, the image data clipping module 52 is configured to use the gdal.Warp function of Python to clip the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

[0103] The device provided in this embodiment can accurately extract image data corresponding to the greenhouse, eliminate interference from irrelevant areas, ensure that the data fits the actual area of ​​the greenhouse in spatial scope, and provide an accurate and focused image basis for subsequent related analysis such as greenhouse snow clearing and greenhouse closing progress monitoring.

[0104] In one embodiment, the greenhouse snow index calculation formula is as follows:

[0105] GSCI=NDSI*(1-R blue );

[0106] Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blueRepresents the blue band reflectance.

[0107] In one embodiment, the classification statistics module 54 includes a calculation unit 5401 , a classification unit 5402 and a statistics unit 5403 .

[0108] The calculation unit 5401 is used to calculate the greenhouse snow index grid map of the target Sentinel-2 image data by using the gdal and numpy functions of python.

[0109] The classification unit 5402 is used to classify the snow-cleared sheds using the Fisher-Jenks algorithm to obtain classification results: sheds that have been cleared of snow and sheds that have not been cleared of snow.

[0110] The statistical unit 5403 is used to use Python to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, obtain the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot, and obtain the area and proportion of the statistical classification results.

[0111] The device provided in this embodiment uses Python related functions and algorithms to accurately calculate the greenhouse snow accumulation index of the target image data and generate a raster map. It distinguishes the snow clearing and greenhouse covering status through a classification algorithm, and then zoning statistics based on vector data. Finally, it quantifies the area and proportion of snow clearing and greenhouse covering conditions in each greenhouse plot, providing accurate data support for intuitively grasping the progress of snow clearing and greenhouse covering and carrying out targeted agricultural management.

[0112] The embodiment of the present invention is an apparatus embodiment corresponding to the above-mentioned method embodiment. The specific operations of the processing steps of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0113] like Figure 6 As shown, the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for monitoring the progress of snow clearing and covering the greenhouse in the above-mentioned embodiment is implemented; or when the computer program is executed by a processor, the method for monitoring the progress of snow clearing and covering the greenhouse based on Sentinel-2 images in the above-mentioned embodiment is implemented.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0115] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A method for monitoring the progress of snow clearing and shed covering based on Sentinel-2 images, characterized in that: The following steps are involved: Acquire multiple periods of Sentinel-2 image data for snow clearing and shed closing within a preset time range and construct a time series image dataset; Acquire vector basic data of the greenhouse, and clip the time series image data set based on the vector basic data to obtain target Sentinel-2 image data of the greenhouse; The greenhouse snow index is constructed based on the normalized difference snow index and blue band reflectance; Calculate the greenhouse snow accumulation index raster map of the target Sentinel-2 image data, use the Fisher-Jenks algorithm to classify snow removal and greenhouse closing, and count the area and proportion of the classification results.

2. The method for monitoring snow clearing and snow cover progress based on Sentinel-2 images as claimed in claim 1, characterized in that: The method of clipping the time series image data set based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse specifically includes the following steps: The gdal.Warp function of Python is used to clip the time series image dataset based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

3. The method for monitoring snow clearing and shed closing progress based on Sentinel-2 images as claimed in claim 1, characterized in that: The greenhouse snow index calculation formula is as follows: GSCI=NDSI*(1-R blue ); Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blue Represents the blue band reflectance.

4. The method for monitoring snow clearing and snow cover progress based on Sentinel-2 images as claimed in claim 1, characterized in that: The method of calculating the greenhouse snow accumulation index grid map of the target Sentinel-2 image data, using the Fisher-Jenks algorithm to classify snow removal and greenhouse closing, and statistically analyzing the area and proportion of the classification results specifically includes the following steps: The greenhouse snow index grid map of the target Sentinel-2 image data is calculated using python's gdal and numpy functions; Fisher-Jenks algorithm was used to classify snow-cleared sheds, and the classification results were: sheds that had been cleared of snow and sheds that had not been cleared of snow; Python is used to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, and the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot are obtained to obtain the area and proportion of the statistical classification results.

5. A snow-clearing and snow-covering progress monitoring device based on Sentinel-2 images, characterized in that: It includes image data acquisition module, image data clipping module, greenhouse snow index construction module and classification statistics module; The image data acquisition module is used to acquire multiple periods of Sentinel-2 image data of snow clearing and shed closing within a preset time range to construct a time series image data set; The image data clipping module is used to obtain vector basic data of the greenhouse, and clip the time series image data set based on the vector basic data to obtain target Sentinel-2 image data of the greenhouse; The greenhouse snow index construction module is used to construct the greenhouse snow index based on the normalized difference snow index and the blue band reflectivity; The classification statistics module is used to calculate the greenhouse snow index grid map of the target Sentinel-2 image data, use the Fisher-Jenks algorithm to classify snow clearing and greenhouse closing, and count the area and proportion of the classification results.

6. The snow-clearing and snow-covering progress monitoring device based on Sentinel-2 imaging according to claim 5 is characterized in that: The image data clipping module is configured to use Python's gdal.Warp function to clip the time series image data set based on the vector basic data to obtain the target Sentinel-2 image data of the greenhouse.

7. The snow-clearing and snow-covering progress monitoring device based on Sentinel-2 images as claimed in claim 5, characterized in that: The greenhouse snow index calculation formula is as follows: GSCI=NDSI*(1-R blue ); Among them, GSCI stands for greenhouse snow cover index, NDSI stands for normalized difference snow index, and R blue Represents the blue band reflectance.

8. The snow-clearing and snow-covering progress monitoring device based on Sentinel-2 images as claimed in claim 5, characterized in that: The classification and statistics module includes a calculation unit, a classification unit and a statistics unit; The calculation unit is used to calculate the greenhouse snow index grid map of the target Sentinel-2 image data by using python's gdal and numpy functions; The classification unit is used to classify snow-cleared sheds using the Fisher-Jenks algorithm to obtain classification results: snow-cleared sheds and uncleared sheds; The statistical unit is used to use Python to perform zoning statistics on the classification results according to the vector basic data of the greenhouse, obtain the pixel count and sum of the cleared snow and uncleaned snow pixels of each greenhouse plot, and obtain the area and proportion of the statistical classification results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for monitoring the progress of snow clearing and roof covering based on Sentinel-2 images as described in any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring the progress of snow clearing and roof covering based on Sentinel-2 images as described in any one of claims 1 to 4 are implemented.

Images